Conference item icon

Conference item

C3DPO: Canonical 3D pose networks for non-rigid structure from motion

Abstract:

We propose C3DPO, a method for extracting 3D models of deformable objects from 2D keypoint annotations in unconstrained images. We do so by learning a deep network that reconstructs a 3D object from a single view at a time, accounting for partial occlusions, and explicitly factoring the effects of viewpoint changes and object deformations. In order to achieve this factorization, we introduce a novel regularization technique. We first show that the factorization is successful if, and only if, ...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:
Publisher copy:
10.1109/ICCV.2019.00778

Authors


More by this author
Institution:
University of Oxford
Department:
Engineering Science
Oxford college:
New College
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Oxford college:
New College
Role:
Author
Host title:
International Conference on Computer Vision (ICCV), 2019
Publication date:
2020-02-27
Acceptance date:
2019-07-22
Event title:
2019 IEEE/CVF International Conference on Computer Vision (ICCV)
Event location:
Seoul, Korea
Event website:
http://iccv2019.thecvf.com/
Event start date:
2019-10-27T00:00:00Z
Event end date:
2019-11-02T00:00:00Z
DOI:
ISSN:
2380-7504
Source identifiers:
1063397
ISBN:
978-1-7281-4803-8
Keywords:
Pubs id:
pubs:1063397
UUID:
uuid:4851bf46-998f-4d20-9f9a-dc57c7bf29ca
Local pid:
pubs:1063397
Deposit date:
2019-10-17

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP